Balling defect prediction in additive manufacturing using machine learning

Producing defect-free, high-quality additive manufacturing parts in a time-efficient and cost-effective way is a major challenge to the materials community. Defects can be caused by complex mechanisms depending on a large range of process parameters and material properties. Currently, there is are no way to predict and reduce defects in additive manufacturing based on scientific principles. A recourse is to synthesize machine learning, experimental data, and mechanistic models to understand defect formation. In this research, we propose an easy-to-use, verifiable balling susceptibility index using supervised machine learning to forecast and reduce the balling defect in laser assistant powder bed fusion.
DebRoy Research Group